Integrative Data Augmentation with U-Net Segmentation Masks Improves Detection of Lymph Node Metastases in Breast Cancer Patients

Simple Summary In recent years many successful models have been developed to perform various tasks in digital histopathology, yet, there is still a reluctance to fully embrace the new technologies in clinical settings. One of the reasons for this is that although these models have achieved high performance at the patch-level, their performance at the image-level can still be underwhelming. Through this study, our main objective was to investigate whether integrating multiple extracted histological features to the input image had potential to further improve the performance of classifier models at the patch-level. Ideally, by achieving 100% accuracy at the patch-level, one can achieve 100% accuracy at the image-level. We hope that our research will entice the community to develop new strategies to further improve performance of existing state-of-the-art models, and facilitate their adoption in the clinics. Deep learning models have potential to improve performance of automated computer-assisted diagnosis tools in digital histopathology and reduce subjectivity. The main objective of this study was to further improve diagnostic potential of convolutional neural networks (CNNs) in detection of lymph node metastasis in breast cancer patients by integrative augmentation of input images with multiple segmentation channels. For this retrospective study, we used the PatchCamelyon dataset, consisting of 327,680 histopathology images of lymph node sections from breast cancer. Images had labels for the presence or absence of metastatic tissue. In addition, we used four separate histopathology datasets with annotations for nucleus, mitosis, tubule, and epithelium to train four instances of U-net. Then our baseline model was trained with and without additional segmentation channels and their performances were compared. Integrated gradient was used to visualize model attribution. The model trained with concatenation/integration of original input plus four additional segmentation channels, which we refer to as ConcatNet, was superior (AUC 0.924) compared to baseline with or without augmentations (AUC 0.854; 0.884). Baseline model trained with one additional segmentation channel showed intermediate performance (AUC 0.870-0.895). ConcatNet had sensitivity of 82.0% and specificity of 87.8%, which was an improvement in performance over the baseline (sensitivity of 74.6%; specificity of 80.4%). Integrated gradients showed that models trained with additional segmentation channels had improved focus on particular areas of the image containing aberrant cells. Augmenting images with additional segmentation channels improved baseline model performance as well as its ability to focus on discrete areas of the image.